Inoenderera Batching Quiz

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

1. Ndeipi kushaya simba kukuru kweiyo static (yakagadziriswa) batching yeLLM inoshumira?
   • Inogona chete kumhanya paCPUs
   • Zvinoda kunyora data rese kutanga
   • Zvikumbiro zvipfupi zvinopera nekukurumidza asi nzvimbo dzadzo dzisina basa apo batch yakamirira iyo yakareba kwazvo
   • Inoita kuti modhi iite zvishoma
2. Ndeipi granularity iyo kuenderera mberi batching kunowedzera nekubvisa zvikumbiro?
   • Kamwe pazuva
   • Per decoding nhanho (chiratidzo chimwe panguva)
   • Nechikumbiro chakazara chete
   • Nenguva yekudzidziswa
3. A continuous-batching request finishes and frees capacity. What can the scheduler do next?
   • Restart every remaining request from its first token
   • Guarantee every queued request runs immediately
   • Discard the finished answer without returning it
   • Admit eligible queued work if its resource budgets allow
4. Ndeipi nzira inoenderana neyakajairwa neinoenderera batching kuita kuisa / kubvisa kutevedzana kwakachipa?
   • PagedAttention's block-based KV cache
   • FP32 kunyatsojeka kaviri
   • Disk swapping
   • Manual data labeling
5. Nderipi bepa rekutsvagisa rinowanzo kurumbidzwa nekufarisa iteration-level (inoenderera) batching?
   • Pepa rekutanga reTransformer
   • The Orca bepa
   • A 1980s database bepa
   • Iyo ImageNet bepa
6. What utilization problem can continuous batching reduce compared with a fixed request batch?
   • Every model accuracy error
   • The need to store any KV cache
   • All queueing at any traffic rate
   • Waiting for the longest request before admitting new eligible work
7. A continuous-batching server has reached its memory budget. Must a newly arrived request enter the next iteration?
   • No; admission can wait until suitable capacity is available
   • Yes; the name guarantees unlimited request admission
   • Yes; the server removes all active outputs automatically
   • Only if the request has no punctuation
8. A long prompt’s prefill delays tokens for already decoding requests. Which serving objective exposes that tradeoff?
   • Measure only the weight-file name
   • Assume more admitted prompts always improve every latency
   • Measure time between decode tokens alongside throughput
   • Count only the number of model layers